def test_diffusion_embedding_two_components_no_diffusion_time(seed=36):
"""Test spectral embedding with two components"""
random_state = np.random.RandomState(seed)
n_sample = 100
affinity = np.zeros(shape=[n_sample * 2, n_sample * 2])
# first component
affinity[0:n_sample,
0:n_sample] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# second component
affinity[n_sample::,
n_sample::] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# connection
affinity[0, n_sample + 1] = 1
affinity[n_sample + 1, 0] = 1
affinity.flat[::2 * n_sample + 1] = 0
affinity = 0.5 * (affinity + affinity.T)
true_label = np.zeros(shape=2 * n_sample)
true_label[0:n_sample] = 1
geom_params = {'laplacian_method': 'geometric'}
se_precomp = SpectralEmbedding(n_components=1,
random_state=np.random.RandomState(seed),
eigen_solver='arpack',
diffusion_maps=True,
geom=geom_params)
embedded_coordinate = se_precomp.fit_transform(affinity,
input_type='affinity')
# thresholding on the first components using 0.
label_ = np.array(embedded_coordinate.ravel() < 0, dtype="float")
assert_equal(normalized_mutual_info_score(true_label, label_), 1.0)
def test_diffusion_embedding_two_components_no_diffusion_time(seed=36):
"""Test spectral embedding with two components"""
random_state = np.random.RandomState(seed)
n_sample = 100
affinity = np.zeros(shape=[n_sample * 2,
n_sample * 2])
# first component
affinity[0:n_sample,
0:n_sample] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# second component
affinity[n_sample::,
n_sample::] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# connection
affinity[0, n_sample + 1] = 1
affinity[n_sample + 1, 0] = 1
affinity.flat[::2 * n_sample + 1] = 0
affinity = 0.5 * (affinity + affinity.T)
true_label = np.zeros(shape=2 * n_sample)
true_label[0:n_sample] = 1
geom_params = {'laplacian_method':'geometric'}
se_precomp = SpectralEmbedding(n_components=1,
random_state=np.random.RandomState(seed),
eigen_solver = 'arpack',
diffusion_maps = True,
geom = geom_params)
embedded_coordinate = se_precomp.fit_transform(affinity,
input_type='affinity')
# thresholding on the first components using 0.
label_ = np.array(embedded_coordinate.ravel() < 0, dtype="float")
assert_equal(normalized_mutual_info_score(true_label, label_), 1.0)
def test_predict_error_no_data(seed=36):
""" Test predict raises an error when data X are not passed"""
radius = 4.0
se = SpectralEmbedding(n_components=2,
random_state=np.random.RandomState(seed))
G = geom.Geometry(adjacency_method = 'brute', adjacency_kwds = {'radius':radius},
affinity_kwds = {'radius':radius})
G.set_data_matrix(S)
S_test = S[-100:, :]
A = G.compute_affinity_matrix()
embed = se.fit_transform(A, input_type = 'affinity')
msg = 'method only implemented when X passed as data'
assert_raise_message(NotImplementedError, msg, se.predict, S_test)
def test_predict_error_no_data(seed=36):
""" Test predict raises an error when data X are not passed"""
radius = 4.0
se = SpectralEmbedding(n_components=2,
random_state=np.random.RandomState(seed))
G = geom.Geometry(adjacency_method='brute',
adjacency_kwds={'radius': radius},
affinity_kwds={'radius': radius})
G.set_data_matrix(S)
S_test = S[-100:, :]
A = G.compute_affinity_matrix()
embed = se.fit_transform(A, input_type='affinity')
msg = 'method only implemented when X passed as data'
assert_raise_message(NotImplementedError, msg, se.predict, S_test)
def check_size(diffusion_maps):
radius = 4.0
geom_params = {'affinity_kwds':{'radius':radius}, 'adjacency_kwds':{'radius':radius}, 'adjacency_method':'brute',
'laplacian_method':'geometric'}
se = SpectralEmbedding(n_components=2,eigen_solver="arpack",
random_state=np.random.RandomState(seed), geom = geom_params)
S_train = S[:900,:]
S_test = S[-100:, :]
embed_train= se.fit_transform(S_train)
embed_test, embed_total = se.predict(S_test)
assert(embed_test.shape[0] == S_test.shape[0])
assert(embed_test.shape[1] == embed_train.shape[1])
assert(embed_total.shape[0] == S.shape[0])
assert(embed_total.shape[1] == embed_train.shape[1])
def test_spectral_embedding_symmetrzation(seed=36):
"""Test spectral embedding with amg solver vs arpack using non symmetric laplacian"""
radius = 4.0
geom_params = {'affinity_kwds':{'radius':radius}, 'adjacency_kwds':{'radius':radius}, 'adjacency_method':'brute',
'laplacian_method':'geometric'}
try:
import pyamg
except ImportError:
raise SkipTest("pyamg not available.")
se_amg = SpectralEmbedding(n_components=2,eigen_solver="amg",
random_state=np.random.RandomState(seed), geom = geom_params)
se_arpack = SpectralEmbedding(n_components=2, eigen_solver="arpack", geom = geom_params,
random_state=np.random.RandomState(seed))
embed_amg = se_amg.fit_transform(S)
embed_arpack = se_arpack.fit_transform(S)
assert_true(_check_with_col_sign_flipping(embed_amg, embed_arpack, 0.05))
def test_spectral_embedding_precomputed_affinity(seed=36,almost_equal_decimals=5):
"""Test spectral embedding with precomputed kernel"""
radius = 4.0
se_precomp = SpectralEmbedding(n_components=2,
random_state=np.random.RandomState(seed))
geom_params = {'affinity_kwds':{'radius':radius}, 'adjacency_kwds':{'radius':radius},
'adjacency_method':'brute'}
se_rbf = SpectralEmbedding(n_components=2, random_state=np.random.RandomState(seed),
geom = geom_params)
G = geom.Geometry(adjacency_method = 'brute', adjacency_kwds = {'radius':radius},
affinity_kwds = {'radius':radius})
G.set_data_matrix(S)
A = G.compute_affinity_matrix()
embed_precomp = se_precomp.fit_transform(A, input_type = 'affinity')
embed_rbf = se_rbf.fit_transform(S, input_type = 'data')
assert_array_almost_equal(
se_precomp.affinity_matrix_.todense(), se_rbf.affinity_matrix_.todense(),
almost_equal_decimals)
assert_true(_check_with_col_sign_flipping(embed_precomp, embed_rbf, 0.05))
def test_spectral_embedding_symmetrzation(seed=36):
"""Test spectral embedding with amg solver vs arpack using non symmetric laplacian"""
radius = 4.0
geom_params = {
'affinity_kwds': {
'radius': radius
},
'adjacency_kwds': {
'radius': radius
},
'adjacency_method': 'brute',
'laplacian_method': 'geometric'
}
try:
import pyamg
except ImportError:
raise SkipTest("pyamg not available.")
se_amg = SpectralEmbedding(n_components=2,
eigen_solver="amg",
random_state=np.random.RandomState(seed),
geom=geom_params)
se_arpack = SpectralEmbedding(n_components=2,
eigen_solver="arpack",
geom=geom_params,
random_state=np.random.RandomState(seed))
embed_amg = se_amg.fit_transform(S)
embed_arpack = se_arpack.fit_transform(S)
assert_true(_check_with_col_sign_flipping(embed_amg, embed_arpack, 0.05))
def test_spectral_embedding_precomputed_affinity(seed=36,
almost_equal_decimals=5):
"""Test spectral embedding with precomputed kernel"""
radius = 4.0
se_precomp = SpectralEmbedding(n_components=2,
random_state=np.random.RandomState(seed))
geom_params = {
'affinity_kwds': {
'radius': radius
},
'adjacency_kwds': {
'radius': radius
},
'adjacency_method': 'brute'
}
se_rbf = SpectralEmbedding(n_components=2,
random_state=np.random.RandomState(seed),
geom=geom_params)
G = geom.Geometry(adjacency_method='brute',
adjacency_kwds={'radius': radius},
affinity_kwds={'radius': radius})
G.set_data_matrix(S)
A = G.compute_affinity_matrix()
embed_precomp = se_precomp.fit_transform(A, input_type='affinity')
embed_rbf = se_rbf.fit_transform(S, input_type='data')
assert_array_almost_equal(se_precomp.affinity_matrix_.todense(),
se_rbf.affinity_matrix_.todense(),
almost_equal_decimals)
assert_true(_check_with_col_sign_flipping(embed_precomp, embed_rbf, 0.05))
def check_size(diffusion_maps):
radius = 4.0
geom_params = {
'affinity_kwds': {
'radius': radius
},
'adjacency_kwds': {
'radius': radius
},
'adjacency_method': 'brute',
'laplacian_method': 'geometric'
}
se = SpectralEmbedding(n_components=2,
eigen_solver="arpack",
random_state=np.random.RandomState(seed),
geom=geom_params)
S_train = S[:900, :]
S_test = S[-100:, :]
embed_train = se.fit_transform(S_train)
embed_test, embed_total = se.predict(S_test)
assert (embed_test.shape[0] == S_test.shape[0])
assert (embed_test.shape[1] == embed_train.shape[1])
assert (embed_total.shape[0] == S.shape[0])
assert (embed_total.shape[1] == embed_train.shape[1])
def test_predict_error_not_fitted(seed=36):
""" Test predict function raises an error when .fit() has not been called"""
radius = 4.0
geom_params = {
'affinity_kwds': {
'radius': radius
},
'adjacency_kwds': {
'radius': radius
},
'adjacency_method': 'brute',
'laplacian_method': 'geometric'
}
se = SpectralEmbedding(n_components=2,
eigen_solver="arpack",
random_state=np.random.RandomState(seed),
geom=geom_params)
S_train = S[:900, :]
S_test = S[-100:, :]
msg = 'the .fit() function must be called before the .predict() function'
assert_raise_message(RuntimeError, msg, se.predict, S_test)
def test_spectral_embedding_unknown_eigensolver(seed=36):
"""Test that SpectralClustering fails with an unknown eigensolver"""
se = SpectralEmbedding(n_components=1,
random_state=np.random.RandomState(seed),
eigen_solver="<unknown>")
assert_raises(ValueError, se.fit, S)
